Papers by Aswin Suresh
Discovering Lobby-Parliamentarian Alignments through NLP (2024.naacl-long)
Copied to clipboard
Aswin Suresh, Lazar Radojević, Francesco Salvi, Antoine Magron, Victor Kristof, Matthias Grossglauser
| Challenge: | Influence of interest groups on parliamentarians and subversion of electorate to determine policy has led to demands from groups such as Transparency International . |
| Approach: | They collect datasets of lobbies’ position papers and MEPs’ speeches and compare them on the basis of semantic similarity and entailment. |
| Outcome: | The proposed method performs significantly better than baselines and matches the public meetings of MEPs with retweet links. |
It’s All Relative: Learning Interpretable Models for Scoring Subjective Bias in Documents from Pairwise Comparisons (2024.eacl-long)
Copied to clipboard
| Challenge: | a new model to score subjective bias in documents is developed to perform pairwise comparisons . a recent study shows that the model can be explained and validated for other domains based on the training data. |
| Approach: | They propose an interpretable model to score subjective bias in Wikipedia articles . they train the model on pairs of revisions of the same Wikipedia article . |
| Outcome: | The proposed model can interpret parameters to discover words most indicative of bias . it compares legal texts, news media and law amendments in three settings . |